© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    Code/Configuration Files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gestone
    -0.68
     Monfieur
    -0.68
     esterni
    -0.66
     internetowa
    -0.66
     itſelf
    -0.65
     uſed
    -0.65
     myſelf
    -0.65
    Geografia
    -0.63
     Theſe
    -0.63
    Jeografia
    -0.62
    POSITIVE LOGITS
     Bill
    0.60
    VIAF
    0.47
     Joe
    0.45
    BILL
    0.45
     BILL
    0.44
     bill
    0.43
     File
    0.43
     Jo
    0.41
    Bill
    0.41
    colgroup
    0.41
    Activations Density 0.006%

    No Known Activations